© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37049
    Prev
    Next
    INDEX
    Explanations

    building companies and careers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç°§
    -0.09
    elig
    -0.09
    æģŃ
    -0.09
    éĻį临
    -0.09
    Cum
    -0.09
    åĬŁè¯¾
    -0.08
     Arm
    -0.08
    æľĭ
    -0.08
    ç´¯
    -0.08
    orm
    -0.08
    POSITIVE LOGITS
    åĵģçīĮ
    0.17
    åĵģçīĮçļĦ
    0.15
    çļĦåĵģçīĮ
    0.14
    çŁ¥åIJįåĵģçīĮ
    0.14
     brands
    0.13
     brand
    0.12
    brands
    0.12
     branding
    0.12
     Brand
    0.12
    ãĥĸãĥ©ãĥ³ãĥī
    0.12
    Activations Density 0.102%

    No Known Activations